Artificial Intelligence · arXiv:2609.02217 v1 · submitted 2 Sep 2026 · 58 references
SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams
The paper says
“LLM agents increasingly self-improve by writing and reusing textual skills, kept either as one global document or as a flat pool of per-task entries, though most of the evidence comes from domains with structurally similar tasks.”
more of the abstract
On long-horizon workloads where each task demands a different solution, the two forms fail in opposite ways: the document collapses into generic discipline, while the pool inflates and its entries stay bound to the instance that wrote them. We argue the missing unit of reuse is the solving procedure shared by a cluster of related tasks, and build SkillGLoW (Global-Local Weave) around it: the local skills a task writes from its own execution are aggregated into procedural families and compressed into de-instantiated global priors, while the instance detail they hold is regenerated per task rather than stored; a commit gate admits a prior only when real execution shows it does not degrade the deployed library. Across four benchmarks (mathematical reasoning, terminal automation, software repair, and embodied control) and three models, the priors gain 17.2 points (hard) over the no-skill baseline on average, with positive gains in all 12 continual-improvement runs, and 18.0 with local regeneration, while the library holds one prior per procedural family, 3.6x more compact than the per-task pool. Under the same protocol GLoW leads a published single-document optimizer on 15 of 21 cells. Unmodified, the library lifts success on unseen ALFWorld tasks from 73.9% to 83.9%, evidence that what transfers is procedure rather than task memory.
from the abstract
Pith says
Machine review · deepseek-v4-flash · 8 Sep 2026 · what was read was not recorded · not checked by a person
It can be wrong. Challenge this review or reply to it.
The passes disagreed. Reader: holds up. Skeptic: agrees with the reader. Referee: major revision.
Procedural families are the right granularity for task-skill reuse, but the clustering quality that makes the whole thing work is only properly validated on one of four benchmarks. This line is wrong
2 major objections · 5 minor
How often objections from reviews like this one are right: not yet measured
Not checked: figures, code, what the 58 references say.
The paper says, at §3.3, §4.4, App. G (Tables A13–A16, A24–A27; Fig. A3)
The review did not quote this passage.
Pith says: Objection 1 of 2 · major
The headline mechanism — that the clustering recovers procedural rather than topical families, and that this is why family consolidation beats all alternative organizations — is validated quantitatively only on ALFWorld (Table A13: ARI 0.605, purity 0.950, NMI 0.801), the only benchmark with independent solution-type labels.
more of objection 1
The TBP outcome-based check (Tables A15–A16) is genuinely convincing: the byte-scanning family prior repaired only the two tasks whose actual solving procedure operates at byte level, and the failed members split along procedure rather than subject matter. For SWE and LMB, however, the evidence stops at family-composition tables and generated signatures (Tables A24–A27); no analysis shows that per-family gains concentrate in families whose members truly share a solving procedure, and Appendix K states explicitly that no sensitivity analysis is reported for the view weights (selected on ALFWorld plus one external domain, Table A4), the 0.45 recall threshold, or the automatic K. The Table 2 ablations compare the full pipeline with and without the family layer, so they do not isolate the clustering algorithm: a plausible alternative is that the gains come from the compression prompt's explicit robustness to noisy clusters (Fig. A3) plus the commit gate, with the specific grouping contributing little. I request (a) a within-system control at matched K using topical-only or random grouping, or ALFWorld's oracle labels, and (b) an outcome-based family-quality analysis for SWE and LMB along the lines of Table A15, using the shipped run artefacts — e.g., whether families whose members share the extracted procedure signature show the fix/break concentration the mechanism predicts.
The paper says, at §3.5, §4.5, App. F
The review did not quote this passage.
Pith says: Objection 2 of 2 · major
The unconditional component G_base is injected into every task's context, yet its content, origin, and contribution are never quantified: the paper does not report what G_base contains, how often Recall's top-1 actually fires above the 0.45 threshold per benchmark, or how much of the Global arm's +17.2 pp would remain with G_base alone.
more of objection 2
Because Local-only (Table 2) carries no G_base and Global-only always carries it, the decomposition of the headline gain between the unconditioned base prior and the per-family priors is not identifiable from the reported cells. This matters for the §4.5 transfer claim ("the prior alone carries the gain"): without routing statistics, a reader cannot tell whether the unseen-task improvement is carried by the family priors or by the fixed base component. Reporting the firing rates and adding a G_base-only control (or a No-Skill + G_base cell) would close the gap and is consistent with the paper's existing run and measurement logic.
5 minor objections
The paper says, at §D.1
Pith says: minor objection 1 of 5
The paired sign and Wilcoxon tests treat the 12 cells as exchangeable, but the three cells within each benchmark share the same task stream and are therefore structurally correlated; a sentence acknowledging this would be appropriate, though the 12/12 unanimity is extreme enough that even a conservative effective sample leaves p well below conventional thresholds.
The paper says, at Table 1 (Avg. soft)
Pith says: minor objection 2 of 5
The Avg. soft column averages soft metrics that live on different scales, as Appendix A itself notes; a footnote on Table 1 warning that only within-row relative movement is meaningful would prevent casual misreading of the 13.0-point average soft gain.
show 3 more
The paper says, at §I / reproducibility
Pith says: minor objection 3 of 5
Appendix I ships per-run artefacts and split files but gives no statement about releasing the pipeline code; given that the clustering and gate logic are implementation-sensitive, an explicit code-release plan would materially strengthen reproducibility.
The paper says, at §3.4 / App. D.3
Pith says: minor objection 4 of 5
The gate's decision to admit on a tie is disclosed and examined in Appendix D.3 but not flagged in the main text; one clause in §3.4 noting that tie-admission is a deliberate, untested design choice would keep the body's claims aligned with the appendix.
The paper says, at Table A25
Pith says: minor objection 5 of 5
Two distinct ALFWorld families are printed under the same generated name (household_object_pick-cool-place); since Appendix N.2 already warns that names are not the clustering axis, a disambiguating suffix would remove a needless obstacle for readers.
What would settle it
On one benchmark without ground-truth families (e.g., SWE-bench Verified, 20 training tasks), have three independent human annotators manually group the tasks into procedural families (using task descriptions and solving procedures from trajectories). Compute the Adjusted Rand Index (ARI) between the human-annotated families and the automatic families produced by GLoW's consensus clustering on that benchmark. If ARI >= 0.4, the clustering is at least moderately reliable; if ARI < 0.2, the clustering assumption fails materially.
from the skeptic's reading
How the review went
4 readings by deepseek-v4-flash · 8 Sep 2026
- Reader holds up
- Skeptic agrees
- Editor wrote the verdict above
- Referee major revision: 2 major objections, 5 minor
Not run on this paper: the simulated authors' defence.
Pith did not check this review's objections against the paper.
The review in full
The review in brief, machine-written
What you should know: this paper makes a clean argument that the missing unit of skill reuse in long-horizon LLM agent systems is the solving procedure shared by a cluster of tasks—the procedural family—and builds a full pipeline (GLoW) around it. The experimental protocol is unusually thorough: 12 runs across 4 benchmarks and 3 models, every comparison on the same splits, statistical significance at p=0.000488, and a nice ablation of the commit gate. The mean gain of 17.2 points over no-skill is consistently positive and well above the measured reproduction dispersion (2.71 pp). The paper also shows that the compressed libraries are 3.6× smaller than a per-task pool and that the priors transfer to unseen tasks. The qualitative excerpts of what a prior keeps versus what it drops are persuasive.
The soft spot—and it's the one the stress test flags—is that the multi-view fusion weights and consensus clustering are validated quantitatively only on ALFWorld (Table 3, ARI 0.605). For Terminal-Bench-Pro, SWE-bench, and LiveMathematicianBench, the paper offers qualitative family inspection (Appendix G.2, N) but no independent ground-truth agreement measure. The view weights were tuned on ALFWorld alone and then frozen; the 0.45 similarity threshold and Kneedle clustering are global. If clustering fails to recover true procedural families on these benchmarks, the claimed advantage could come more from the commit gate or local regeneration than from the family unit itself. The paper acknowledges this limitation but does not fix it with evidence.
That said, the central idea is sound and the rest of the evidence supports it: the family structure on ALFWorld matches the dataset's own labels, the compression examples show genuine de-instantiation, and the transfer results show that the library carries reusable procedure rather than task memory. The clustering weakness is real but not fatal—it would be good to see a second quantitative validation on at least one more benchmark, or a comparison against a simpler clustering baseline.
Who is this for? Anyone working on skill management for LLM agents, especially on heterogeneous task streams. The paper deserves a serious referee; it is a solid contribution that identifies a previously unarticulated granularity problem and implements a working solution. I would cite it for the conceptual framing if nothing else, and I'd bring it to reading group to discuss the trade-off between clustering complexity and generalizability.
The strongest objection
The central claim that procedural families are the missing unit of reuse rests on the clustering step's ability to group tasks that share a solving procedure. The multi-view fusion weights were tuned on ALFWorld alone (Appendix B, Table A4), and the 0.45 similarity threshold and Kneedle clustering are fixed across all four benchmarks and three models. The paper validates clustering quality quantitatively only on ALFWorld (Table 3, ARI 0.605, purity 0.950). For Terminal-Bench-Pro, SWE-bench, and LiveMathematicianBench, the paper provides qualitative inspection (Appendix G.2 for TBP; Appendix N for SWE and LMB) and family composition tables, but no quantitative agreement measure against an independent ground truth. Without such validation, it is not established that the clustering recovers true procedural families on these benchmarks. If the clustering instead groups by surface subject matter or noisy embeddings, the compressed global priors would be generic or misaligned, and the claimed advantage—17.2 points over no-skill—could be driven by the commit gate or local regeneration rather than by the procedural family unit. The ablations (Base-only vs. GLoW) demonstrate that family granularity matters, but they do not isolate the quality of the specific clustering algorithm used; a different clustering method might yield similar or better gains. The paper acknowledges this limitation but does not address it with independent evidence on the three unlabeled benchmarks. This is the weakest load-bearing link in the argument.
The reader identified the reliability of multi-view fusion and consensus clustering as the weakest assumption, noting that the weights were chosen on only one benchmark and not independently verified on the other three. I agree that this is the most load-bearing concern, as the whole concept of procedural families depends on accurate clustering. However, the paper provides substantial end-to-end evidence (12 runs, positive gains in all, p=0.000488, ablations, transfer results) that the method works under this assumption. The clustering quality on ALFWorld is good (ARI 0.605, purity 0.95) and qualitative inspection on TBP supports face validity. While I would have liked quantitative validation on at least one more benchmark, the existing evidence is sufficient to accept the paper. Therefore I recommend the verdict remain unchanged (ACCEPT).
The referee's report
The contribution is significant if the mechanism holds: it identifies a granularity of skill reuse between the single document and the per-task entry and provides an unusually rigorous evaluation — 12 fixed continual runs with paired tests at the minimum attainable p-value, a measured reproduction dispersion of 2.71 pp against a mean gain of 17.2 pp, honest peak-over-rounds disclosure restricted to admitted libraries, a single fixed hyperparameter set per benchmark family (Appendix K), shipped run artefacts and split files, and a carefully aligned SkillOpt comparison. The paper's own falsifiable checks deserve explicit credit: the byte-level procedure test on TBP (Tables A15–A16) and the predicted ordering that family granularity pays off most where a single document has the least to summarize. Its limitations are stated candidly. The load-bearing weakness is that quantitative validation of the procedural-clustering axis exists only on ALFWorld; for the other three benchmarks the evidence is qualitative or outcome-based, so the mechanism claim is defensible but not fully established.
Pith's reading of the paper (a machine's summary, not the authors')
The paper argues that the dominant two forms of LLM agent skill organization—a single global document and a flat per-task pool—both fail on long-horizon workloads where each task demands a different solution. The global document collapses into generic discipline, while the per-task pool inflates and its entries are bound to the instance that wrote them. The proposed unit of reuse is the solving procedure shared by a cluster of related tasks, which the authors call a procedural family. Around this unit they build SkillGLoW (GLoW), which groups local skills into families, compresses each family into a de-instantiated global prior that retains only the shared procedure, and gates long-term updates by real execution. Across four benchmarks and three models, the frozen priors gain 17.2 points (hard) over a no-skill baseline with a library 3.6× more compact than the per-task pool, and the library transfers unmodified to unseen tasks.
What carries the argument. The central object is the procedural family, defined as a set of tasks whose local skills share a solving procedure. The key mechanism is the global–local weave: a global layer holds one de-instantiated prior per family (produced by consensus clustering of skill cards and LLM-based compression), and a local layer is regenerated per task from its own execution feedback. A verifier-grounded commit gate admits a candidate revision only when its measured deployment value meets or exceeds the standing library's value (up to a noise tolerance of ϵ = 0.02). The clustering uses five textual views of each skill card (signature compact, signature verbose, instruction, trajectory, full skill) fused with fixed weights (0.30/0.20/0.20/0.20/0.10) so that grouping follows procedure rather than wording.
Core claim. On long-horizon heterogeneous task streams, neither a single global document nor a flat per-task library provides effective skill reuse. The missing unit is the procedural family: a cluster of tasks that share a solving procedure. GLoW operationalizes this unit by (i) extracting local skills from each task's own execution trajectories, (ii) clustering those skills into procedural families via multi-view consensus clustering, (iii) compressing each family into a de-instantiated global prior that retains only the shared procedure (applicability conditions, core steps, common failure modes), and (iv) committing the prior only if its real execution on the training stream does not degrade the deployed library. At solving time, the frozen prior is woven with a freshly regenerated local skill that supplies instance detail. The result is a bounded library (one prior per family) that nevertheless lifts performance on all 12 runs (mean +17.2 hard points) and transfers to unseen tasks (ALFWorld from 73.9% to 83.9%).
The premise it rests on. The multi-view fusion weights (0.30/0.20/0.20/0.20/0.10), similarity threshold (0.45), and consensus clustering parameters were fixed based on a sweep on ALFWorld alone and then applied unchanged to all other benchmarks and models; if the clustering fails to recover true procedural families on a new stream, the global priors become generic or noisy and the entire pipeline loses its advantage.
If the paper is right (Pith's inferences, not the authors')
Skill libraries for long-horizon agents can remain bounded (one prior per procedural family) regardless of the number of tasks seen, solving the unbounded-growth problem of flat pools.
De-instantiated global priors transfer across tasks within a family without memorizing instance details, as shown by the 10-point lift on unseen ALFWorld tasks.
The verifier-grounded commit gate prevents performance degradation from over-compressed or mis-clustered priors, rejecting 7 of 26 candidates across 12 runs.
Consolidation into families naturally discovers cross-task procedural structure even when tasks belong to different domains, e.g., terminal tasks that both operate at the byte level.
The framework predicts that family granularity pays off most where a single document has no dominant procedure (software repair, terminal tasks), which is exactly where the largest gains are observed.
The procedural-family unit may generalize beyond LLM agents to any system that accumulates reusable knowledge from multiple instances, such as robotic skill libraries or program synthesis from demonstrations.
Because the global priors are plain text, they could in principle be inherited across different base models without retraining, opening a path to cross-model skill transfer that the paper leaves untested.
The fixed view weights and similarity threshold (tuned on ALFWorld alone) raise the question of whether a more adaptive clustering mechanism—e.g., learning the weights or threshold online—could improve robustness on highly diverse streams.
If the commit gate is removed, performance drops from +14.7 to +9.6 points on average, suggesting that execution-gated admission is a critical component that simpler baselines (e.g., AWM) lack.
Check this review
Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.
How often reviews like this one are right
Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.
How often objections from reviews like this one are right: not yet measured
Reviews by people
This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.
The paper
Abstract
LLM agents increasingly self-improve by writing and reusing textual skills, kept either as one global document or as a flat pool of per-task entries, though most of the evidence comes from domains with structurally similar tasks. On long-horizon workloads where each task demands a different solution, the two forms fail in opposite ways: the document collapses into generic discipline, while the pool inflates and its entries stay bound to the instance that wrote them. We argue the missing unit of reuse is the solving procedure shared by a cluster of related tasks, and build SkillGLoW (Global-Local Weave) around it: the local skills a task writes from its own execution are aggregated into procedural families and compressed into de-instantiated global priors, while the instance detail they hold is regenerated per task rather than stored; a commit gate admits a prior only when real execution shows it does not degrade the deployed library. Across four benchmarks (mathematical reasoning, terminal automation, software repair, and embodied control) and three models, the priors gain 17.2 points (hard) over the no-skill baseline on average, with positive gains in all 12 continual-improvement runs, and 18.0 with local regeneration, while the library holds one prior per procedural family, 3.6x more compact than the per-task pool. Under the same protocol GLoW leads a published single-document optimizer on 15 of 21 cells. Unmodified, the library lifts success on unseen ALFWorld tasks from 73.9% to 83.9%, evidence that what transfers is procedure rather than task memory.
The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.
abstract compiled · 2026-09-23
The authors' main claim, as the classifier picked it out 0.40
“Unmodified, the library lifts success on unseen ALFWorld tasks from 73.9% to 83.9%, evidence that what transfers is procedure rather than task memory.”
How the main claim is stated: asserted 0.92
What the abstract itself states, as probabilities: claims first 0.08 · states limitation 0.25 · human participants 0.03 · controlled comparison 0.97 · randomized assignment 0.02 · states quantitative result 0.99 · compares with prior results 0.98 · mentions code or data availability 0.03
The abstract, sentence by sentence
This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.
| Sentence | Role | The authors' own work | States the main conclusion | Strength |
|---|---|---|---|---|
| LLM agents increasingly self-improve by writing and reusing textual skills, kept either as one global document or as a flat pool of per-task entries, though most of the evidence comes from domains with structurally similar tasks. | background 1.00 | 0.06 | 0.03 | asserted 0.97 |
| On long-horizon workloads where each task demands a different solution, the two forms fail in opposite ways: the document collapses into generic discipline, while the pool inflates and its entries stay bound to the instance that wrote them. | gap 0.60 | 0.20 | 0.08 | asserted 1.00 |
| We argue the missing unit of reuse is the solving procedure shared by a cluster of related tasks, and build SkillGLoW (Global-Local Weave) around it: the local skills a task writes from its own execution are aggregated into procedural families and compressed into de-instantiated global priors, while the instance detail they hold is regenerated per task rather than stored; a commit gate admits a prior only when real execution shows it does not degrade the deployed library. | method 0.80 | 0.89 | 0.45 | asserted 0.94 |
| Across four benchmarks (mathematical reasoning, terminal automation, software repair, and embodied control) and three models, the priors gain 17.2 points (hard) over the no-skill baseline on average, with positive gains in all 12 continual-improvement runs, and 18.0 with local regeneration, while the library holds one prior per procedural family, 3.6x more compact than the per-task pool. | result 1.00 | 0.96 | 0.37 | asserted 1.00 |
| Under the same protocol GLoW leads a published single-document optimizer on 15 of 21 cells. | result 1.00 | 0.87 | 0.09 | asserted 1.00 |
| Unmodified, the library lifts success on unseen ALFWorld tasks from 73.9% to 83.9%, evidence that what transfers is procedure rather than task memory. | interpretation 0.64 | 0.92 | 0.18 | asserted 0.92 |
What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 0.96
What was examined, and what was not
Sources read
- arXiv listing abstract v1
Not examined
- full text
- figures and tables
- references and citing sentences
- relations to other papers
Levels run
- P abstract
Not run
- S sections
- T body sentences
- C citations
- R cross-paper relations
How the labels were made
Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-09-23: 1 request, 5,329 input tokens.
Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON
Figures (3)
References (58)
- [1] Jimenez, Carlos E. and Yang, John and Wettig, Alexander and Yao, Shunyu and Pei, Kexin and Press, Ofir and Narasimhan, Karthik , title =. International Conference on Learning Representations (ICLR) , year = on Pith
- [2] Merrill, Mike A. and Shaw, Alexander G. and Carlini, Nicholas and Li, Boxuan and Raj, Harsh and Bercovich, Ivan and Shi, Lin and Shin, Jeong Yeon and Walshe, Thomas and Buchanan, E. Kelly and Shen, Junhong and Ye, Guanghao and Lin, Haowei and Poulos, Jason and Wang, Maoyu and ... on Pith
- [3] Wang, Weixun and Xu, XiaoXiao and An, Wanhe and Dai, Fangwen and Gao, Wei and others , title =. 2025 , eprint = on Pith
- [4] He, Linyang and Yu, Qiyao and Dong, Hanze and Liao, Baohao and Xu, Xinxing and Goldblum, Micah and Bian, Jiang and Mesgarani, Nima , title =. 2026 , eprint = on Pith
- [5] Shridhar, Mohit and Yuan, Xingdi and C. International Conference on Learning Representations (ICLR) , year = on Pith
- [6] Li, Xiangyi and Chen, Wenbo and Liu, Yimin and Zheng, Shenghan and Chen, Xiaokun and others , title =. 2026 , eprint = on Pith
- [7] Zhou, Yingli and Wang, Shu and Su, Yaodong and Du, Wenchuan and Fang, Yixiang and Lin, Xuemin , title =. 2026 , eprint = on Pith
- [8] Yang, Yutao and Li, Junsong and Pan, Qianjun and Zhan, Bihao and Cai, Yuxuan and Du, Lin and Zhou, Jie and Chen, Kai and Chen, Qin and Li, Xin and Zhang, Bo and He, Liang , title =. 2026 , eprint = on Pith
- [9] Ni, Jingwei and Liu, Yihao and Liu, Xinpeng and Sun, Yutao and Zhou, Mengyu and Cheng, Pengyu and Wang, Dexin and Zhao, Erchao and Jiang, Xiaoxi and Jiang, Guanjun , title =. 2026 , eprint = on Pith
- [10] Yang, Yifan and Gong, Ziyang and Huang, Weiquan and Yang, Qihao and Zhou, Ziwei and Huang, Zisu and Li, Yan and Gao, Xuemei and Dai, Qi and Liu, Bei and Qiu, Kai and Yang, Yuqing and Chen, Dongdong and Yang, Xue and Luo, Chong , title =. 2026 , eprint = on Pith
- [11] Kang, Minki and Chen, Wei-Ning and Han, Dongge and Inan, Huseyin A. and Wutschitz, Lukas and Chen, Yanzhi and Sim, Robert and Rajmohan, Saravan , title =. International Conference on Machine Learning , year = on Pith
- [12] Zhou, Huichi and Chen, Yihang and Guo, Siyuan and Yan, Xue and Lee, Kin Hei and Wang, Zihan and Lee, Ka Yiu and Zhang, Guchun and Shao, Kun and Yang, Linyi and Wang, Jun , title =. 2025 , eprint = on Pith
- [13] Zhou, Huichi and Guo, Siyuan and Liu, Anjie and Yu, Zhongwei and Gong, Ziqin and Zhao, Bowen and Chen, Zhixun and Zhang, Menglong and Chen, Yihang and Li, Jinsong and Yang, Runyu and Liu, Qiangbin and Yu, Xinlei and Zhou, Jianmin and Wang, Na and Sun, Chunyang and Wang, Jun , ... on Pith
- [14] Cao, Zouying and Deng, Jiaji and Yu, Li and Zhou, Weikang and Liu, Zhaoyang and Ding, Bolin and Zhao, Hai , title =. Findings of the Association for Computational Linguistics: ACL 2026 , pages =. 2026 , doi = on Pith
- [15] Kim, Kangsan and Kang, Minki and Kim, Taeil and Yang, Yanlai and Ren, Mengye and Hwang, Sung Ju , title =. 2026 , eprint = on Pith
- [16] Jiang, Guanyu and Su, Zhaochen and Qu, Xiaoye and Fung, Yi R. , title =. International Conference on Machine Learning , year = on Pith
- [17] Ouyang, Siru and Yan, Jun and Chen, Yanfei and Han, Rujun and Wang, Zifeng and Dalvi Mishra, Bhavana and Meng, Rui and Li, Chun-Liang and Jiao, Yizhu and Zha, Kaiwen and Shen, Maohao and Tirumalashetty, Vishy and Lee, George and Han, Jiawei and Pfister, Tomas and Lee, Chen-Yu ... on Pith
- [18] Li, Xiaoyuan and Li, Moxin and Bao, Keqin and Ma, Yubo and Wang, Wenjie and Liu, Dayiheng and Feng, Fuli , title =. 2026 , eprint = on Pith
- [19] Pan, Shuai and Liu, Yixiang and Gao, Jiaye and Gao, Te and Liu, Weiwen and Lin, Jianghao and Fu, Zhihui and Wang, Jun and Zhang, Weinan and Yu, Yong , title =. 2026 , eprint = on Pith
- [20] Lin, Huawei and Li, Peng and Song, Jie and Jiang, Fuxin and Zhang, Tieying , title =. 2026 , eprint = on Pith
show 38 more
- [21] Satop. Finding a ``Kneedle'' in a Haystack: Detecting Knee Points in System Behavior , booktitle =. 2011 , doi = on Pith
- [22] Wang, Guanzhi and Xie, Yuqi and Jiang, Yunfan and Mandlekar, Ajay and Xiao, Chaowei and Zhu, Yuke and Fan, Linxi and Anandkumar, Anima , title =. 2023 , eprint = on Pith
- [23] Yao, Shunyu and Zhao, Jeffrey and Yu, Dian and Du, Nan and Shafran, Izhak and Narasimhan, Karthik and Cao, Yuan , title =. International Conference on Learning Representations (ICLR) , year = on Pith
- [24] Shinn, Noah and Cassano, Federico and Gopinath, Ashwin and Narasimhan, Karthik and Yao, Shunyu , title =. Advances in Neural Information Processing Systems (NeurIPS) , volume = on Pith
- [25] Schick, Timo and Dwivedi-Yu, Jane and Dess. Toolformer: Language Models Can Teach Themselves to Use Tools , booktitle = on Pith
- [26] Reimers, Nils and Gurevych, Iryna , title =. Conference on Empirical Methods in Natural Language Processing (EMNLP-IJCNLP) , pages =. 2019 , doi = on Pith
- [27] Ouyang, Siru and Yan, Jun and Hsu, I-Hung and Chen, Yanfei and Jiang, Ke and Wang, Zifeng and Han, Rujun and Le, Long T. and Daruki, Samira and Tang, Xiangru and Tirumalashetty, Vishy and Lee, George and Rofouei, Mahsan and Lin, Hangfei and Han, Jiawei and Lee, Chen-Yu and Pfi... on Pith
- [28] Tang, Xiangru and Qin, Tianrui and Peng, Tianhao and Zhou, Ziyang and Shao, Daniel and Du, Tingting and Wei, Xinming and Xia, Peng and Wu, Fang and Zhu, He and Zhang, Ge and Liu, Jiaheng and Wang, Xingyao and Hong, Sirui and Wu, Chenglin and Cheng, Hao and Wang, Chi and Zhou, ... on Pith
- [29] Du, Jiawei and Wu, Jinlong and Chen, Yuzheng and Hu, Yucheng and Li, Bing and Zhou, Joey Tianyi , title =. 2025 , eprint = on Pith
- [30] Zheng, Boyuan and Fatemi, Michael Y. and Jin, Xiaolong and Wang, Zora Zhiruo and Gandhi, Apurva and Song, Yueqi and Gu, Yu and Srinivasa, Jayanth and Liu, Gaowen and Neubig, Graham and Su, Yu , title =. 2025 , eprint = on Pith
- [31] Zhang, Ziao and Shi, Kou and Huang, Shiting and Nie, Avery and Zeng, Yu and Zhao, Yiming and Fang, Zhen and Su, Qishen and Qiu, Haibo and Yang, Wei and Ren, Qingnan and Zou, Shun and Huang, Wenxuan and Chen, Lin and Chen, Zehui and Zhao, Feng , title =. 2026 , eprint = on Pith
- [32] Yuksekgonul, Mert and Bianchi, Federico and Boen, Joseph and Liu, Sheng and Lu, Pan and Huang, Zhi and Guestrin, Carlos and Zou, James , title =. Nature , volume =. 2025 , doi = on Pith
- [33] Khattab, Omar and Singhvi, Arnav and Maheshwari, Paridhi and Zhang, Zhiyuan and Santhanam, Keshav and Vardhamanan, Sri and Haq, Saiful and Sharma, Ashutosh and Joshi, Thomas T. and Moazam, Hanna and Miller, Heather and Zaharia, Matei and Potts, Christopher , title =. Internati... on Pith
- [34] Yang, Chengrun and Wang, Xuezhi and Lu, Yifeng and Liu, Hanxiao and Le, Quoc V. and Zhou, Denny and Chen, Xinyun , title =. International Conference on Learning Representations (ICLR) , year = on Pith
- [35] Madaan, Aman and Tandon, Niket and Gupta, Prakhar and Hallinan, Skyler and Gao, Luyu and Wiegreffe, Sarah and Alon, Uri and Dziri, Nouha and Prabhumoye, Shrimai and Yang, Yiming and Gupta, Shashank and Majumder, Bodhisattwa Prasad and Hermann, Katherine and Welleck, Sean and Y... on Pith
- [36] Zhao, Andrew and Huang, Daniel and Xu, Quentin and Lin, Matthieu and Liu, Yong-Jin and Huang, Gao , title =. AAAI Conference on Artificial Intelligence (AAAI) , year = on Pith
- [37] Yang, John and Jimenez, Carlos E. and Wettig, Alexander and Lieret, Kilian and Yao, Shunyu and Narasimhan, Karthik and Press, Ofir , title =. Advances in Neural Information Processing Systems (NeurIPS) , volume = on Pith
- [38] Liu, Xiao and Yu, Hao and Zhang, Hanchen and Xu, Yifan and Lei, Xuanyu and Lai, Hanyu and Gu, Yu and Ding, Hangliang and Men, Kaiwen and Yang, Kejuan and Zhang, Shudan and Deng, Xiang and Zeng, Aohan and Du, Zhengxiao and Zhang, Chenhui and Shen, Sheng and Zhang, Tianjun and S... on Pith
- [39] Mialon, Gr. International Conference on Learning Representations (ICLR) , year = on Pith
- [40] Monti, Stefano and Tamayo, Pablo and Mesirov, Jill and Golub, Todd , title =. Machine Learning , volume =. 2003 , doi = on Pith
- [41] Rousseeuw, Peter J. , title =. Journal of Computational and Applied Mathematics , volume =. 1987 , doi = on Pith
- [42] Ward, Jr., Joe H. , title =. Journal of the American Statistical Association , volume =. 1963 , doi = on Pith
- [43] Fang, Runnan and Liang, Yuan and Wang, Xiaobin and Wu, Jialong and Qiao, Shuofei and Xie, Pengjun and Huang, Fei and Chen, Huajun and Zhang, Ningyu , title =. Findings of the Association for Computational Linguistics: ACL 2026 , pages =. 2026 , doi = on Pith
- [44] Wang, Zora Zhiruo and Mao, Jiayuan and Fried, Daniel and Neubig, Graham , title =. Proceedings of the 42nd International Conference on Machine Learning , volume = on Pith
- [45] Suzgun, Mirac and Yuksekgonul, Mert and Bianchi, Federico and Jurafsky, Dan and Zou, James , title =. 2025 , eprint = on Pith
- [46] Han, Tingxu and Zhang, Yi and Song, Wei and Fang, Chunrong and Chen, Zhenyu and Sun, Youcheng and Hu, Lijie , title =. 2026 , eprint = on Pith
- [47] Zhang, Yanzhao and Li, Mingxin and Long, Dingkun and Zhang, Xin and Lin, Huan and Yang, Baosong and Xie, Pengjun and Yang, An and Liu, Dayiheng and Lin, Junyang and Huang, Fei and Zhou, Jingren , title =. 2025 , eprint = on Pith
- [48] Clancey, William J. Communication, Simulation, and Intelligent Agents: Implications of Personal Intelligent Machines for Medical Education. Proceedings of the Eighth International Joint Conference on Artificial Intelligence (IJCAI-83) on Pith
- [49] Clancey, William J. Classification Problem Solving. Proceedings of the Fourth National Conference on Artificial Intelligence on Pith
- [50] Robinson, Arthur L. , title =. 1980 , doi =. https://science.sciencemag.org/content/208/4447/1019.full.pdf , journal = on Pith
- [51] Robinson, Arthur L. New Ways to Make Microcircuits Smaller---Duplicate Entry. Science on Pith
- [52] Diane Warner Hasling and William J. Clancey and Glenn Rennels , abstract =. Strategic explanations for a diagnostic consultation system , journal =. 1984 , issn =. doi:https://doi.org/10.1016/S0020-7373(84)80003-6 , url = on Pithdoi:10.1016/s0020-7373(84)80003-6
- [53] Hasling, Diane Warner and Clancey, William J. and Rennels, Glenn R. and Test, Thomas. Strategic Explanations in Consultation---Duplicate. The International Journal of Man-Machine Studies on Pith
- [54] Rice, James. Poligon: A System for Parallel Problem Solving on Pith
- [55] Clancey, William J. Transfer of Rule-Based Expertise through a Tutorial Dialogue on Pith
- [56] Clancey, William J. The Engineering of Qualitative Models on Pith
- [57] Attention Is All You Need , author=. 2023 , eprint= on Pith
- [58] NASA. Pluto: The 'Other' Red Planet on Pith
Cited by 2 Pith papers
Reviewed papers on Pith that cite this one. OpenAlex reports about 3 citations worldwide. The full citation record
- SkillDuet: Co-Evolving Models and Skills through Response Feedback cs.AI · Nov 2026
- Mining Agent Skills from Production Traces cs.AI · Oct 2026
Challenges and discussion
Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.
Come back by email
A short list of the week's newly reviewed papers. Nothing is sent until you confirm from your inbox, and every email has a link that stops it. No account.



No comments yet.
Sign in to comment